Mercurial > repos > brinkmanlab > mauve_contig_mover
comparison mauve_contig_mover.xml @ 0:c14690ec0c9f draft
"planemo upload for repository https://github.com/brinkmanlab/galaxy-tools/tree/master/mauve_contig_mover commit 33b02e08cbc8f76fb4b8537f8c968393f85a1b5e"
author | brinkmanlab |
---|---|
date | Fri, 24 Jan 2020 17:43:19 -0500 |
parents | |
children | f8b09693c9c1 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:c14690ec0c9f |
---|---|
1 <tool id="mauve-contig-mover" name="Mauve Contig Mover" version="1.0" profile="16.04"> | |
2 <description>Reorder a multi-contig dataset against a reference genome</description> | |
3 <edam_topics> | |
4 <edam_topic>topic_0196</edam_topic> | |
5 <edam_topic>topic_0091</edam_topic> | |
6 </edam_topics> | |
7 <edam_operations> | |
8 <edam_operation>operation_0495</edam_operation> | |
9 <edam_operation>operation_0491</edam_operation> | |
10 </edam_operations> | |
11 <requirements> | |
12 <requirement type="package" version="2.4.0.snapshot_2015_02_13">mauve</requirement> | |
13 </requirements> | |
14 <version_command>mauveAligner --version</version_command> | |
15 <command detect_errors="exit_code"><![CDATA[ | |
16 #if $ref_select.ref_source == "db" | |
17 #set global $index = $ref_select.ref_db | |
18 #else if $ref_select.ref_source == "meta" | |
19 #set global $index = $data.metadata.dbkey | |
20 #else if $ref_select.ref_source == "key" | |
21 #set global $index = $ref_select.key | |
22 #else | |
23 #set global $index = None | |
24 #set $ref = $ref_select.ref | |
25 #if $ref.is_of_type("genbank") | |
26 ln -sf $ref `basename $ref`.gbk && | |
27 #set $ref = $os.path.basename(str($ref)) + ".gbk" | |
28 #end if | |
29 #end if | |
30 | |
31 #if $index | |
32 ## Get path to database file | |
33 #try | |
34 #set $ref = next(record for record in $__app__.tool_data_tables['all_fasta'].get_fields() if str( record[1] ) == str( $index ))[-1] | |
35 #except StopIteration | |
36 #raise ValueError('Reference not found: '+str($index)) | |
37 #end try | |
38 #end if | |
39 | |
40 #if $draft.is_of_type("genbank") | |
41 ln -sf $draft `basename ${draft}.gbk` && | |
42 #set $draft_path = $os.path.basename(str($draft)) + ".gbk" | |
43 #else | |
44 #set $draft_path = str($draft) | |
45 #end if | |
46 | |
47 MauveCM -output output -ref $ref -draft $draft_path && $__tool_directory__/mcm_final.sh | |
48 ]]></command> | |
49 <inputs> | |
50 <param name="draft" type="data" format="genbank,fasta" label="Draft" /> | |
51 <conditional name="ref_select"> | |
52 <param name="ref_source" type="select" label="Select the source of the reference to align the draft to"> | |
53 <option value="db">Data manager</option> | |
54 <option value="file">History</option> | |
55 <option value="meta" selected="true">Input Metadata</option> | |
56 <option value="key">Key</option> | |
57 </param> | |
58 <when value="file"> | |
59 <param name="ref" type="data" format="genbank,fasta" label="Reference" /> | |
60 </when> | |
61 <when value="db"> | |
62 <param name="ref_db" type="select" label="Using reference genome" help="Select genome from the list"> | |
63 <options from_data_table="all_fasta"> | |
64 <filter type="sort_by" column="2" /> | |
65 </options> | |
66 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
67 </param> | |
68 </when> | |
69 <when value="meta"> | |
70 </when> | |
71 <when value="key"> | |
72 <!-- this is a workaround until https://github.com/galaxyproject/galaxy/issues/7496 is resolved --> | |
73 <param name="key" type="text" label="Provide a dbkey to use" /> | |
74 </when> | |
75 </conditional> | |
76 </inputs> | |
77 <outputs> | |
78 <data name="reordered" format="fasta" from_work_dir="final.reordered" label="${tool.name} on ${on_string}: Reordered" /> | |
79 <data name="backbone" format="tabular" from_work_dir="final.backbone" label="${tool.name} on ${on_string}: Backbone" /> | |
80 <data name="contigs" format="tabular" from_work_dir="final.contigs.tab" label="${tool.name} on ${on_string}: Contig Order" /> | |
81 <data name="features" format="tabular" from_work_dir="final.features.tab" label="${tool.name} on ${on_string}: Features"> | |
82 <filter>hasattr(draft, 'is_of_type') and draft.is_of_type("genbank")</filter> | |
83 </data> | |
84 </outputs> | |
85 <tests> | |
86 <test expect_failure="true"> | |
87 <!-- Mauve uses biojava which currently has a bug: https://github.com/biojava/biojava/issues/843 --> | |
88 <param name="draft" value="test-data/draft.gbff" ftype="genbank" /> | |
89 <conditional name="ref_select"> | |
90 <param name="ref_source" value="file" /> | |
91 <param name="ref" value="test-data/ref.gbff" ftype="genbank" /> | |
92 </conditional> | |
93 </test> | |
94 <test expect_num_outputs="4"> | |
95 <param name="draft" value="test-data/draft_bioperl.gbff" ftype="genbank" /> | |
96 <conditional name="ref_select"> | |
97 <param name="ref_source" value="file" /> | |
98 <param name="ref" value="test-data/ref_bioperl.gbff" ftype="genbank" /> | |
99 </conditional> | |
100 <output name="reordered" checksum="sha256:2a5e621227f4967337cefd68273f78d3390c94f5fd7ce4dcbf8024a342aeb976" ftype="fasta" /> | |
101 <output name="backbone" checksum="sha256:f46966bcaed3324e43cad91161f380427a7d3cc52bbf823ae811d3f5dfaf2927" ftype="tabular" /> | |
102 <output name="contigs" file="test-data/contig_order.tabular" ftype="tabular" /> | |
103 <output name="features" checksum="sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" ftype="tabular" /> | |
104 </test> | |
105 </tests> | |
106 <help><![CDATA[ | |
107 The Mauve Contig Mover (MCM) can be used to order a draft genome relative to a related reference genome. | |
108 The functionality of this software module has been described in Rissman et al. 2009, a publication in Bioinformatics. | |
109 The Mauve Contig Mover can ease a comparative study between draft and reference sequences by ordering draft contigs according to the reference genome. | |
110 In many cases, true rearrangements in the draft relative to the reference can be identified. The quality of the reorder is limited by the distance between | |
111 the sequences, as indicated by the amount of shared gene content among the two organisms. A more distant reference will usually yield fewer ordered draft genome contigs, | |
112 and may also induce erroneous placements of draft contigs. In addition to ordering contigs, MCM also orient them in the most likely orientation, and, if annotated sequence | |
113 features are specified in an input file (e.g. with GenBank format input for the draft), MCM will output adjusted coordinates ranges for the features. | |
114 | |
115 Outputs: | |
116 | |
117 "Backbone" is the backbone output by mauveAligner representing the alignements. | |
118 | |
119 "Reordered" is a fasta file with the contigs reordered. Contigs aligned in reverse will be thier compliment sequence. | |
120 | |
121 "Contig Order" acts as an index to the fasta as the contig orders and orientations change (even if the draft was originally | |
122 input as a genbank, after the first alignment, it will be converted to a fasta with annotation information preserved in a file described below). | |
123 The file is divided into 3 sections, each containing a list of contigs. The data for each contig includes its label (name), | |
124 its location in the genome (numbered in pseudocoordinates from the first to last contig, and whether it is oriented the same as originally input, | |
125 or was complemented. | |
126 | |
127 The three sections are described below: | |
128 | |
129 Contigs to reverse: | |
130 This section contains contigs whose order is reversed with respect to the previous iteration. | |
131 Note that contigs in this section may be oriented the same as originally input, this can be determined from the forward orcomplement designation. | |
132 | |
133 Ordered Contings: | |
134 This is a list of all the contigs in the order and orientation they appear in the fasta for the draft of this iteration of the reorder. | |
135 Since these include all the contigs in the original input, those with no ordering information (no aligned region) will be clustered at the end. | |
136 These will appear as contigs with no LCBs at the end of the draft genome. | |
137 | |
138 Contigs with Conflicting Order information: | |
139 This is a list of contigs containing LCBs suggesting multiple possible locations. | |
140 These may be of interest to verify positioning, or to look at points of potential rearrangement or misassembly. | |
141 | |
142 If the draft was input as an annotated genbank file, a second file will appear called "Features". This file will contain a line for each annotation, | |
143 information about its current orientation and location (which will change if the contig is inverted), coordinates from the previous iteration (indicating | |
144 relative orientation), and whether it is reversed from the original input. It will also have a label field used to identify each feature. | |
145 This will be gotten from the annotation, as checked in the following order: db_xref, label, gene, and locus_tag. | |
146 ]]></help> | |
147 <citations> | |
148 <citation type="doi">10.5281/zenodo.3364789</citation> | |
149 <citation type="doi">10.1093/bioinformatics/btp356</citation> | |
150 </citations> | |
151 </tool> |